Peter Shen of Siemens Healthineers, at HIMSS 2024 commenting on the need for better reimbursement of AI algorithms in healthcare.

Imaging Wire Sponsors

Bayer  •  Blackford  •  CARPL.ai  •  Clearpath  •  DeepHealth  •  Enlitic  •  Gleamer  •  Intelerad  •  Medality  •  Merge by Merative  •  Nuance  •  PocketHealth  •  Riverain Technologies  •  Siemens Healthineers  •  SpinTech MRI  •  TeraRecon  •  United Imaging  •  Us2.ai  •  Visage Imaging

CT Scanners

Predicting Patient Follow-Up for Imaging Exams

There’s nothing more frustrating than patients who don’t comply with follow-up imaging recommendations. But a new study in JACR not only identifies the factors that can lead to patient non-compliance, it also points the way toward IT tools that could predict who will fall short – and help direct targeted outreach efforts.

The new study focuses specifically on incidental pulmonary nodules, a particularly thorny problem in radiology, especially as CT lung cancer screening ramps up around the world.

• Prevalence of these nodules can range from 24-51% based on different populations, and while most are benign, a missed nodule could develop into a late-stage lung cancer with poor patient survival. 

Researchers from the University of Pennsylvania wanted to test a set of 13 clinical and socioeconomic factors that could predict lack of follow-up in a group of 1.6k patients who got CT scans from 2016 to 2019. 

• Next, they evaluated how well these factors worked when fed into several different types of homegrown machine learning models – precursors of a tool that could be implemented clinically – finding …

• Clinical setting had the strongest association in predicting non-adherence, with patients seen in the inpatient or emergency setting far more likely skip follow-up compared to outpatients (OR=7.3 and 8.6)
• Patients on Medicaid were more likely to skip follow-up compared to those on Medicare (OR=2)
• On the other hand, patients with high-risk nodules were less likely to skip follow-up compared to those at low risk (OR=0.25) 
• Comorbidity was the only one of the 13 factors that was not predictive of follow-up 

The authors hypothesized that the strong association between clinical setting and follow-up was due to the different socio-demographic characteristics of patients typically seen in each environment. 

• Patients in the outpatient setting often have access to more resources like health insurance, transportation, and health literacy, while those without such resources often have to resort to the emergency department or hospital wards when they become sick enough to require care.

In the next step of the study, the data were fed into four types of machine learning algorithms; all turned in good performance for predicting follow-up adherence, with AUCs ranging from 0.76-0.80. 

The Takeaway

It’s not hard to see the findings from this study ultimately making their way into clinical use as part of some sort of commercial machine-learning algorithm that helps clinicians manage incidental findings. Stay tuned.

AI in Radiology and the Considerations for Regulation

AI in healthcare has grown quickly, as have discussions about AI regulation. Listen to this on-demand webinar from Bayer and Calantic Digital Solutions to hear expert perspectives on the current and future state of AI governance in healthcare and radiology.

The Smooth Deployment of Lung AI

Seamless use of AI wouldn’t be possible without workflow integration, made possible in collaboration with hospital IT teams. Learn about the smooth deployment of DeepHealth’s Saige Lung solution at Portsmouth Hospitals University NHS Trust in the UK.

The Wire

• News from HIMSS: This week marked the first HIMSS meeting since the society sold the trade show side of its business to UK B2B giant Informa last year. Early indications are that preliminary attendance at HIMSS 2024 is comparable to HIMSS 2023, when some 35k attendees convened in Chicago. That compares to about 43k conference-goers in 2019, before the COVID-19 pandemic, but attendance on the exhibit floor this year seems strong. AI has been a major focus this week, but most sessions are discussing using the technology for healthcare applications outside of radiology. 

• Providers Get on AI Safety TRAIN: One of the biggest stories at HIMSS this week was the announcement of TRAIN (Trustworthy & Responsible AI Network), a consortium of blue-chip universities joining forces to ensure the rollout of safer and more reliable AI algorithms. The consortium is based on Microsoft technology, and plans to promote safer AI by sharing best practices for using AI, providing tools for measuring AI-enabled outcomes, and creating a national registry to capture real-world outcomes related to efficacy, safety, and optimization of AI algorithms.

• CT Contrast Reactions Are Rare: A massive study out of China found an extremely low rate of reactions to nonionic iodinated contrast media for CT exams. In European Radiology, researchers analyzed contrast reactions in 473k patients who got outpatient scans from 2017-2021, finding a low rate of adverse drug reactions (0.11%) and an even lower rate of acute-related drug reactions (0.099%). Some agents had slightly higher reaction rates, but of the entire population only two patients experienced a serious adverse reaction. 

• Premier Partners with Ferrum, Deploys Gleamer AI: Teleradiology services provider Premier Radiology Services is rolling out Gleamer’s BoneView AI algorithm for fracture detection as part of a new partnership with AI platform provider Ferrum Health. Premier will consolidate its AI infrastructure on the Ferrum platform, giving it not only easier AI deployment but also access to clinical analytics. Ferrum has been expanding its operations since raising $6M in January 2023, while Premier in February acquired subspecialty teleradiology firm NationalRad. 

• Docs Take Dim View of PE: A new survey published this week in JAMA Internal Medicine came to a not-so-shocking conclusion: physicians have a largely negative opinion of private equity investment in healthcare. Researchers surveyed 525 US doctors (67% general internal medicine physicians), finding that 61% viewed PE negatively, 29% were neutral, and 11% had a favorable opinion. Doctors saw PE negatively with respect to physician well-being (58%), healthcare prices (57%), and health equity (51%). Interestingly, only 5.5% of respondents worked for a PE-acquired healthcare entity.

• FTC to Probe PE in Healthcare: In related news, the US Federal Trade Commission said last week it was launching a probe into the growing role of PE in healthcare. The agency is looking for details on PE transactions that could increase consolidation and generate profits while harming patient health, worker safety, and quality and affordability of care. The FTC is taking comments through May 6.

• ScreenPoint Deploys AI at Johns Hopkins: ScreenPoint Medical has signed a deal to deploy its Transpara AI technology for breast screening at Johns Hopkins. The deal lands ScreenPoint a prestigious new customer for Transpara, which is coming off a series of positive papers on its use in European screening programs.  The Johns Hopkins breast imaging service team performs over 77k breast imaging exams and 5k interventional procedures a year.

• FDA Releases Extended Reality Infographics: In a move that may or may not be related to the release of the Apple Vision Pro spatial computing headset, the FDA has published a pair of infographics covering the medical use of extended reality – augmented and virtual reality. The infographics address the benefits and risks of extended reality, with one targeted at patients and the other at providers. It’s a worthy goal, but the text-heavy design of the infographics almost requires a special headset just to be readable.

• Avatar Medical Raises $5.4M: While we’re on the subject of extended reality, French 3D software developer Avatar Medical raised $5.4M to commercialize the company’s technology, which converts medical images into patient-specific avatars. The software has applications for enhancing patient surgical consultations and improving medical education, and received FDA clearance in 2023. Avatar will use the funding for product commercialization in the US and Europe, while also accelerating the development of its AvatarCloud product.

• Gesund Signs AI Testing Deal: AI services provider Gesund.ai has signed a partnership with a Canadian health system to create a real-world environment for testing AI algorithms. Gesund is working with Institute for Better Health at Trillium Health Partners in Toronto to enable developers to use its MLOps platform in combination with IBH physician experts to test their solutions, with the goal of faster translation of research-grade AI to clinical grade AI. The partnership builds on Gesund’s recent moves to expand its footprint in trustworthy AI.  

• GE/MGB Deal on Foundation Models: GE HealthCare and Mass General Brigham have extended their existing AI relationship to include the use of foundation models for developing medical AI algorithms. Foundation models have the potential to enable faster algorithm training and deployment compared to models like convolutional neural networks due to their ability to solve a diverse set of tasks. GE and MGB have been working together on AI since 2017. 

• CT Scans of Animal Specimens: And now for something completely different: A group of natural history museums have completed work on openVertebrate (oVert), a massive project to conduct CT scans of vertebrate animals, reconstruct them into 3D images, and make them available online. Over 13k specimens were scanned, including amphibians, reptiles, fish, and mammals, and contributors had to use creative means to acquire scans of some of the larger animals, like Galapagos tortoises. The images can be accessed by researchers, educators, students, and the public.

The Power of Enterprise Image Exchange

Exchange medical data across the enterprise and grow your referrals and patient transfers. Share images in real-time – no VPN or CDs required – with Intelerad’s Enterprise Image Exchange.

4 Reasons Why Subscription Is Better

The KLAS-leading Intuition advanced visualization solution from TeraRecon includes all the clinical features you need, plus a growing list of exclusive subscription-only content. Learn more about what’s included.

MRI Access and the Cost of Inpatient Stays

Longer inpatient stays due to delayed MRI access are a long-standing and costly issue for hospital systems. Find out how STAGE from SpinTech MRI can reduce your MRI backlog and inpatient stays by shortening brain scan times by 30%.

The Resource Wire

• Blazing the Trail to the Cloud: Come for the hottest imaging technology, stay for the homemade nitro ice cream! Visit Visage Imaging at HIMSS 2024 and learn how they are trailblazing imaging’s SaaS move to the cloud. Schedule a demo today. 

• Stop Shipping Discs! By pivoting to a 100% digital fulfillment model for patient images and records, you can improve their experience while significantly reducing labor and shipping costs. Find out how from Clearpath. 

• Drivers of AI Usage in Radiology: Radiologists are being asked to read more, read faster, and with a higher degree of accuracy as imaging data grows in volume and complexity. In this video, listen to Bernardo Bizzo, MD, and Riverain CEO Steve Worrell explain how this is driving AI usage. 

• Memorial MRI’s Choice for Patient Comfort: Texas has one of the highest obesity rates in the US. So to best serve its patients, Memorial MRI & Diagnostic in Houston turned to United Imaging and its 3.0T uMR OMEGA MRI scanner with 75cm ultra-wide-bore. Learn more about their story. 

• Top 5 Obstacles to Radiology AI Adoption: AI is reshaping healthcare, but some healthcare providers are encountering hurdles that demand strategic approaches for successful implementation. Learn the top 5 obstacles to radiology AI adoption – and how to avoid them – in this blog post from Blackford. 

• The Right Approach to AI Adoption: Discover the right approach to AI adoption and the transformative impact of CARPL.ai in accelerating the clinical implementation of AI, driving ROI, and revolutionizing patient care in this video featuring leaders from Radiology Partners and University Hospitals, Cleveland. 

• Create Better Experiences for Staff and Patients: Visit Merge by Merative at HIMSS 2024 to learn how their solutions, built on a cloud-native foundation, are helping imaging organizations to create better experiences for staff and patients alike. Book a meeting today.

• Solutions to Solve Radiology’s Workflow Challenges: Radiology faces numerous challenges to more efficient workflow, from the siloed nature of healthcare enterprises to mundane tasks that are ripe for automation. In this Imaging Wire Show, we talked to Matthew Lungren, MD, and Calum Cunningham of Nuance Communications.

• Increasing Patient Centricity and Breaking Down Barriers to the Quadruple Aim:  A panel of industry leaders discuss the advantages of a patient-centric approach to image exchange during this RSNA session. Watch the PocketHealth-hosted session here.

• From NASA Engineer to Radiology Leader: Join Medality founder and CEO Daniel Arnold for a discussion on The Radiology Report podcast with John Stewart, MD, PhD, radiologist and CEO of Scriptor Software. Hear him describe his journey from aerospace engineer to radiologist to health IT entrepreneur. 

• A Milestone Study for Cardiac Strain Analysis: Us2.ai’s deep learning algorithm was able to interpret echo AI left ventricular strain images with similar accuracy as conventional measurements. Read all about this milestone study and its implications for patient management in EHJ-Digital Health. 

• Take the Lead in Fracture Detection: A recent review by University College London highlighted essential factors for selecting the right AI tool for fracture detection, with Gleamer’s BoneView emerging as a standout performer. Dive deeper into the article to learn more. 

• Experience Cinematic Reality at HIMSS: Visit the Siemens Healthineers booth at HIMSS 2024 to experience Cinematic Reality, the company’s new app for the Apple Vision Pro spatial computing headset. Book your meeting today.

• Unlock Your Data’s Potential: At HIMSS 2024, learn how Enlitic can improve data quality within medical imaging and unlock the potential of your organization’s healthcare data. Book a demo today.